{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"### Building on the [Kaggle notebook](https://www.kaggle.com/code/lccburk/feature-engineering-and-random-forest-prediction) 📔, only tweaked RandomForest parameters 🌲: `n_estimators` to 125 and `min_samples_leaf` to 10. Achieved an improved leaderboard score of 0.428 👍.\"","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Engineering and Random Forest Prediction to Detect Sleep States","metadata":{}},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport polars as pl\nimport datetime \nfrom tqdm import tqdm\n\nimport plotly.express as px\nfrom plotly.subplots import make_subplots\nimport plotly.graph_objects as go\n\nfrom metric import score # Import event detection ap score function\n\n# These are variables to be used by the score function\ncolumn_names = {\n    'series_id_column_name': 'series_id',\n    'time_column_name': 'step',\n    'event_column_name': 'event',\n    'score_column_name': 'score',\n}\n\ntolerances = {\n    'onset': [12, 36, 60, 90, 120, 150, 180, 240, 300, 360], \n    'wakeup': [12, 36, 60, 90, 120, 150, 180, 240, 300, 360]\n}","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-09-25T11:55:38.017866Z","iopub.execute_input":"2023-09-25T11:55:38.018445Z","iopub.status.idle":"2023-09-25T11:55:39.578559Z","shell.execute_reply.started":"2023-09-25T11:55:38.01841Z","shell.execute_reply":"2023-09-25T11:55:39.577324Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Importing data","metadata":{}},{"cell_type":"code","source":"# Importing data \n\n# Column transformations\n\ndt_transforms = [\n    pl.col('timestamp').str.to_datetime(), \n    (pl.col('timestamp').str.to_datetime().dt.year()-2000).cast(pl.UInt8).alias('year'), \n    pl.col('timestamp').str.to_datetime().dt.month().cast(pl.UInt8).alias('month'),\n    pl.col('timestamp').str.to_datetime().dt.day().cast(pl.UInt8).alias('day'), \n    pl.col('timestamp').str.to_datetime().dt.hour().cast(pl.UInt8).alias('hour')\n]\n\ndata_transforms = [\n    pl.col('anglez').cast(pl.Int16), # Casting anglez to 16 bit integer\n    (pl.col('enmo')*1000).cast(pl.UInt16), # Convert enmo to 16 bit uint\n]\n\ntrain_series = pl.scan_parquet('/kaggle/input/child-mind-institute-detect-sleep-states/train_series.parquet').with_columns(\n    dt_transforms + data_transforms\n    )\n\ntrain_events = pl.read_csv('/kaggle/input/child-mind-institute-detect-sleep-states/train_events.csv').with_columns(\n    dt_transforms\n    )\n\ntest_series = pl.scan_parquet('/kaggle/input/child-mind-institute-detect-sleep-states/test_series.parquet').with_columns(\n    dt_transforms + data_transforms\n    )\n\n# Getting series ids as a list for convenience\nseries_ids = train_events['series_id'].unique(maintain_order=True).to_list()\n\n# Removing series with mismatched counts: \nonset_counts = train_events.filter(pl.col('event')=='onset').group_by('series_id').count().sort('series_id')['count']\nwakeup_counts = train_events.filter(pl.col('event')=='wakeup').group_by('series_id').count().sort('series_id')['count']\n\ncounts = pl.DataFrame({'series_id':sorted(series_ids), 'onset_counts':onset_counts, 'wakeup_counts':wakeup_counts})\ncount_mismatches = counts.filter(counts['onset_counts'] != counts['wakeup_counts'])\n\ntrain_series = train_series.filter(~pl.col('series_id').is_in(count_mismatches['series_id']))\ntrain_events = train_events.filter(~pl.col('series_id').is_in(count_mismatches['series_id']))\n\n# Updating list of series ids, not including series with no non-null values.\nseries_ids = train_events.drop_nulls()['series_id'].unique(maintain_order=True).to_list()","metadata":{"execution":{"iopub.status.busy":"2023-09-25T11:55:39.580228Z","iopub.execute_input":"2023-09-25T11:55:39.581167Z","iopub.status.idle":"2023-09-25T11:55:40.029801Z","shell.execute_reply.started":"2023-09-25T11:55:39.581121Z","shell.execute_reply":"2023-09-25T11:55:40.028283Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature Engineering","metadata":{}},{"cell_type":"code","source":"features, feature_cols = [pl.col('hour')], ['hour']\n\nfor mins in [5, 30, 60*2, 60*8] :\n    features += [\n        pl.col('enmo').rolling_mean(12 * mins, center=True, min_periods=1).abs().cast(pl.UInt16).alias(f'enmo_{mins}m_mean'),\n        pl.col('enmo').rolling_max(12 * mins, center=True, min_periods=1).abs().cast(pl.UInt16).alias(f'enmo_{mins}m_max')\n    ]\n\n    feature_cols += [ \n        f'enmo_{mins}m_mean', f'enmo_{mins}m_max'\n    ]\n\n    # Getting first variations\n    for var in ['enmo', 'anglez'] :\n        features += [\n            (pl.col(var).diff().abs().rolling_mean(12 * mins, center=True, min_periods=1)*10).abs().cast(pl.UInt32).alias(f'{var}_1v_{mins}m_mean'),\n            (pl.col(var).diff().abs().rolling_max(12 * mins, center=True, min_periods=1)*10).abs().cast(pl.UInt32).alias(f'{var}_1v_{mins}m_max')\n        ]\n\n        feature_cols += [ \n            f'{var}_1v_{mins}m_mean', f'{var}_1v_{mins}m_max'\n        ]\n\nid_cols = ['series_id', 'step', 'timestamp']\n\ntrain_series = train_series.with_columns(\n    features\n).select(id_cols + feature_cols)\n\ntest_series = test_series.with_columns(\n    features\n).select(id_cols + feature_cols)","metadata":{"execution":{"iopub.status.busy":"2023-09-25T11:55:40.032226Z","iopub.execute_input":"2023-09-25T11:55:40.032731Z","iopub.status.idle":"2023-09-25T11:55:40.049165Z","shell.execute_reply.started":"2023-09-25T11:55:40.032685Z","shell.execute_reply":"2023-09-25T11:55:40.047311Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def make_train_dataset(train_data, train_events, drop_nulls=False) :\n    \n    series_ids = train_data['series_id'].unique(maintain_order=True).to_list()\n    X, y = pl.DataFrame(), pl.DataFrame()\n    for idx in tqdm(series_ids) : \n        \n        # Normalizing sample features\n        sample = train_data.filter(pl.col('series_id')==idx).with_columns(\n            [(pl.col(col) / pl.col(col).std()).cast(pl.Float32) for col in feature_cols if col != 'hour']\n        )\n        \n        events = train_events.filter(pl.col('series_id')==idx)\n        \n        if drop_nulls : \n            # Removing datapoints on dates where no data was recorded\n            sample = sample.filter(\n                pl.col('timestamp').dt.date().is_in(events['timestamp'].dt.date())\n            )\n        \n        X = X.vstack(sample[id_cols + feature_cols])\n\n        onsets = events.filter((pl.col('event') == 'onset') & (pl.col('step') != None))['step'].to_list()\n        wakeups = events.filter((pl.col('event') == 'wakeup') & (pl.col('step') != None))['step'].to_list()\n\n        # NOTE: This will break if there are event series without any recorded onsets or wakeups\n        y = y.vstack(sample.with_columns(\n            sum([(onset <= pl.col('step')) & (pl.col('step') <= wakeup) for onset, wakeup in zip(onsets, wakeups)]).cast(pl.Boolean).alias('asleep')\n            ).select('asleep')\n            )\n    \n    y = y.to_numpy().ravel()\n    \n    return X, y","metadata":{"execution":{"iopub.status.busy":"2023-09-25T11:55:40.051132Z","iopub.execute_input":"2023-09-25T11:55:40.051536Z","iopub.status.idle":"2023-09-25T11:55:40.075912Z","shell.execute_reply.started":"2023-09-25T11:55:40.051502Z","shell.execute_reply":"2023-09-25T11:55:40.074713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_events(series, classifier) :\n    '''\n    Takes a time series and a classifier and returns a formatted submission dataframe.\n    '''\n    \n    series_ids = series['series_id'].unique(maintain_order=True).to_list()\n    events = pl.DataFrame(schema={'series_id':str, 'step':int, 'event':str, 'score':float})\n\n    for idx in tqdm(series_ids) : \n\n        # Collecting sample and normalizing features\n        scale_cols = [col for col in feature_cols if (col != 'hour') & (series[col].std() !=0)]\n        X = series.filter(pl.col('series_id') == idx).select(id_cols + feature_cols).with_columns(\n            [(pl.col(col) / series[col].std()).cast(pl.Float32) for col in scale_cols]\n        )\n\n        # Applying classifier to get predictions and scores\n        preds, probs = classifier.predict(X[feature_cols]), classifier.predict_proba(X[feature_cols])[:, 1]\n\n        #NOTE: Considered using rolling max to get sleep periods excluding <30 min interruptions, but ended up decreasing performance\n        X = X.with_columns(\n            pl.lit(preds).cast(pl.Int8).alias('prediction'), \n            pl.lit(probs).alias('probability')\n                        )\n        \n        # Getting predicted onset and wakeup time steps\n        pred_onsets = X.filter(X['prediction'].diff() > 0)['step'].to_list()\n        pred_wakeups = X.filter(X['prediction'].diff() < 0)['step'].to_list()\n        \n        if len(pred_onsets) > 0 : \n            \n            # Ensuring all predicted sleep periods begin and end\n            if min(pred_wakeups) < min(pred_onsets) : \n                pred_wakeups = pred_wakeups[1:]\n\n            if max(pred_onsets) > max(pred_wakeups) :\n                pred_onsets = pred_onsets[:-1]\n\n            # Keeping sleep periods longer than 30 minutes\n            sleep_periods = [(onset, wakeup) for onset, wakeup in zip(pred_onsets, pred_wakeups) if wakeup - onset >= 12 * 30]\n\n            for onset, wakeup in sleep_periods :\n                # Scoring using mean probability over period\n                score = X.filter((pl.col('step') >= onset) & (pl.col('step') <= wakeup))['probability'].mean()\n\n                # Adding sleep event to dataframe\n                events = events.vstack(pl.DataFrame().with_columns(\n                    pl.Series([idx, idx]).alias('series_id'), \n                    pl.Series([onset, wakeup]).alias('step'),\n                    pl.Series(['onset', 'wakeup']).alias('event'),\n                    pl.Series([score, score]).alias('score')\n                ))\n\n    # Adding row id column\n    events = events.to_pandas().reset_index().rename(columns={'index':'row_id'})\n\n    return events","metadata":{"execution":{"iopub.status.busy":"2023-09-25T11:55:40.077593Z","iopub.execute_input":"2023-09-25T11:55:40.078329Z","iopub.status.idle":"2023-09-25T11:55:40.104678Z","shell.execute_reply.started":"2023-09-25T11:55:40.078282Z","shell.execute_reply":"2023-09-25T11:55:40.103216Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training Models","metadata":{}},{"cell_type":"code","source":"\nfrom sklearn.model_selection import train_test_split\n\ntrain_ids, val_ids = train_test_split(series_ids, train_size=0.7, random_state=42)\n\n# We will collect datapoints at 10 minute intervals for training for validating\ntrain_data = train_series.filter(pl.col('series_id').is_in(train_ids)).take_every(12 * 10).collect()\n\nval_data = train_series.filter(pl.col('series_id').is_in(val_ids)).collect()\nval_solution = train_events.filter(pl.col('series_id').is_in(val_ids)).select(['series_id', 'event', 'step']).to_pandas()\n'''\n# We will collect datapoints and take 1 million samples\ntrain_data = train_series.filter(pl.col('series_id').is_in(series_ids)).collect().sample(int(1e6))\n'''","metadata":{"execution":{"iopub.status.busy":"2023-09-25T11:55:40.108398Z","iopub.execute_input":"2023-09-25T11:55:40.109293Z","iopub.status.idle":"2023-09-25T12:00:38.776933Z","shell.execute_reply.started":"2023-09-25T11:55:40.109244Z","shell.execute_reply":"2023-09-25T12:00:38.775682Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Creating train dataset\nX_train, y_train = make_train_dataset(train_data, train_events)","metadata":{"execution":{"iopub.status.busy":"2023-09-25T12:00:38.77922Z","iopub.execute_input":"2023-09-25T12:00:38.780405Z","iopub.status.idle":"2023-09-25T12:00:41.735928Z","shell.execute_reply.started":"2023-09-25T12:00:38.780355Z","shell.execute_reply":"2023-09-25T12:00:41.734399Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Training and validating random forest","metadata":{}},{"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\n\n# Training classifier\nrf_classifier = RandomForestClassifier(n_estimators=125, # 500\n                                    min_samples_leaf=10, #300\n                                    random_state=42,\n                                    n_jobs=-1)\n\nrf_classifier.fit(X_train[feature_cols], y_train)","metadata":{"execution":{"iopub.status.busy":"2023-09-25T12:00:41.764685Z","iopub.execute_input":"2023-09-25T12:00:41.765057Z","iopub.status.idle":"2023-09-25T12:00:41.781249Z","shell.execute_reply.started":"2023-09-25T12:00:41.765022Z","shell.execute_reply":"2023-09-25T12:00:41.780096Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Checking performance on validation set\nrf_submission = get_events(val_data, rf_classifier)\n\nprint(f\"Random forest score: {score(val_solution, rf_submission, tolerances, **column_names)}\")","metadata":{"execution":{"iopub.status.busy":"2023-09-23T21:53:48.487951Z","iopub.execute_input":"2023-09-23T21:53:48.489308Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Saving classifier \nimport pickle\nwith open('rf_classifier_5m_8h.pkl', 'wb') as f:\n    pickle.dump(rf_classifier, f)\n\n#with open('rf_classifier.pkl', 'rb') as f:\n#    rf_classifier = pickle.load(f)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Training and validating gradient boost","metadata":{}},{"cell_type":"code","source":"'''# With SKL\nfrom sklearn.ensemble import GradientBoostingClassifier\n\ngb_classifier = GradientBoostingClassifier(n_estimators=100, learning_rate=0.05, max_depth=10, random_state=42)\ngb_classifier.fit(X_train[feature_cols], y_train)'''","metadata":{"execution":{"iopub.status.busy":"2023-09-20T00:32:29.342993Z","iopub.execute_input":"2023-09-20T00:32:29.343447Z","iopub.status.idle":"2023-09-20T00:51:55.176259Z","shell.execute_reply.started":"2023-09-20T00:32:29.343416Z","shell.execute_reply":"2023-09-20T00:51:55.174488Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''# Plotting feature importances\npx.bar(x=feature_cols, \n       y=gb_classifier.feature_importances_,\n       title='Gradient boosting feature importances'\n      )'''","metadata":{"execution":{"iopub.status.busy":"2023-09-20T00:51:55.179395Z","iopub.execute_input":"2023-09-20T00:51:55.180376Z","iopub.status.idle":"2023-09-20T00:51:57.466029Z","shell.execute_reply.started":"2023-09-20T00:51:55.180342Z","shell.execute_reply":"2023-09-20T00:51:57.464688Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''\n# Checking performance on validation set\ngb_submission = get_events(val_data, gb_classifier)\n\nprint(f\"Gradient boosting score: {score(val_solution, gb_submission, tolerances, **column_names)}\")\n'''","metadata":{"execution":{"iopub.status.busy":"2023-09-20T00:51:57.467479Z","iopub.execute_input":"2023-09-20T00:51:57.468116Z","iopub.status.idle":"2023-09-20T00:56:51.902928Z","shell.execute_reply.started":"2023-09-20T00:51:57.468082Z","shell.execute_reply":"2023-09-20T00:56:51.901915Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Applying to test data","metadata":{}},{"cell_type":"code","source":"# Recovering memory\ndel train_data ","metadata":{"execution":{"iopub.status.busy":"2023-09-20T05:22:09.101944Z","iopub.execute_input":"2023-09-20T05:22:09.102333Z","iopub.status.idle":"2023-09-20T05:22:09.107008Z","shell.execute_reply.started":"2023-09-20T05:22:09.102306Z","shell.execute_reply":"2023-09-20T05:22:09.106043Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Getting event predictions for test set and saving submission\nsubmission = get_events(test_series.collect(), rf_classifier)\nsubmission.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2023-09-20T05:22:10.01902Z","iopub.execute_input":"2023-09-20T05:22:10.019601Z","iopub.status.idle":"2023-09-20T05:22:10.835397Z","shell.execute_reply.started":"2023-09-20T05:22:10.019563Z","shell.execute_reply":"2023-09-20T05:22:10.83395Z"},"trusted":true},"execution_count":null,"outputs":[]}]}